Design of a Rule Based Bio Medical Entity Extractor 
G. Suganya1, R. Porkodi2
1G.Suganya, Ph.D Research Scholar, Department of Computer Science, Bharathiar University, Coimbatore (Tamil Nadu), India.
2R.Porkodi, Associate Professor, Department of Computer Science, Bharathiar University, Coimbatore (Tamil Nadu), India.
Manuscript received on 25 August 2019 | Revised Manuscript received on 01 September 2019 | Manuscript Published on 14 September 2019 | PP: 245-249 | Volume-8 Issue-5S3, July 2019 | Retrieval Number: E10550785S319/19©BEIESP | DOI: 10.35940/ijeat.E1055.0785S319
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The field of Biomedical Entity Extraction/ Identification plays a vital role in Bioinformatics and rapidly growing to meet the needs of different text mining tasks. Many biomedical entity extraction tools have been developed so far. This research work has focused to develop a Rule based Biomedical Entity Extraction and tested with PubMed Medline abstracts of Colon cancer and Alzheimer disease categories. The proposed Biomedical Entity Extractor gives promising result when compared with existing tools. The proposed method is incorporating of two phases such as preprocessing the input text document using NLP techniques and create the rules to find out the biomedical entities using regular expression. The results of Rule based Biomedical Entity Extractor are validated with the well-known Biomedical Genia tagger and Genecards Database. The method proposed in this paper almost good as genia tagger. The evaluation results on Colon cancer and Alzheimer disease abstracts corpus of Biomedical Entity Extraction achieve an accuracy of 92% and 88% respectively which identifies more number of entities compared to other existing tools.
Keywords: Medline Abstracts, Genia Tagger, Pubtator, BCC-NER, Biomedical Text Mining.
Scope of the Article: Low-power design